Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare a non-read-only but idempotent, non-destructive mutation; the description adds real behavior beyond that: null means revert to the plan's timing/channel, removed:false restores a step, keep:true asserts existing custom text, and addAfter returns the new step's id. The reversible-removal wording is consistent with destructiveHint=false rather than contradicting it. Rate limits and permission requirements are not mentioned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Every clause carries information, but the description is one dense run-on with heavy parenthetical stacking that makes it hard to scan for the right parameter combination. 'as the journey list does' is vague filler, and a short list structure would have front-loaded the mutually exclusive update modes.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter mutation tool with 13% schema coverage and no output schema, the description covers nearly all behavior an agent needs, including the response value for the addAfter case. The remaining gap is task_id, the lead-scoping parameter, which is never explained anywhere in the definition.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With schema description coverage at only 13%, the description does most of the work: it defines null semantics for dueAt and channel, the enum values, the true/false meaning of removed, the const-like role of keep:true, that step_id comes from the lead's journey, and the idempotency_key retry rule. It also adds a constraint absent from the schema (dueAt must stay after the preceding step). task_id is never explained, and addAfter's returned id is only loosely described.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource ('Changes one step of one lead's follow-ups') and adds a parity reference to the journey list, so an agent knows this mutates a single follow-up step. It does not explicitly distinguish itself from close siblings like redraft_lead_step or move_lead_journey, but the resource scope is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete calling patterns: send one or more of dueAt/channel/removed/keep, or addAfter alone. It also implicitly steers away from text editing ('The step's words are your person's to change in the app') and explains the retry rule for idempotency_key. The missing piece is an explicit statement of when to prefer redraft_lead_step or move_lead_journey instead.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.